Remember to use the trigger word jeonheejin. Best results (or maybe not idk) come from using LORA weight 0.6-0.9 and Hires fix with latent bicubic antialiased, 20 steps, 0.5 denoising strength, and 1.25x upscale. I've used ChilloutMix to generate images since the LORA is trained on Basil Mix.
Description
LORA training settings are inspired by Alelele but I trained a much larger dataset on Basil Mix using a longer training time. This is why I recommend a weight of 0.6-0.9.
Details
Downloads
2,558
Platform
SeaArt
Platform Status
Available
Created
4/1/2023
Updated
9/24/2025
Deleted
-
Trigger Words:
jeonheejin